© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48853
    Prev
    Next
    INDEX
    Explanations

    excellence and success

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     डेली
    0.45
     Officers
    0.43
    purpose
    0.41
    rotation
    0.41
     करिकुलम
    0.41
    
    0.41
    éria
    0.40
     образования
    0.39
     devise
    0.39
     ш
    0.39
    POSITIVE LOGITS
     Insp
    0.43
     brilliance
    0.39
    Outstanding
    0.37
     outstanding
    0.37
     ઉ
    0.37
     hugely
    0.37
     Outstanding
    0.36
    בר
    0.35
    Insp
    0.35
     rich
    0.35
    Activations Density 0.004%

    No Known Activations